Continual Reinforcement Learning with TELLA

TL;DR

TELLA is a tool designed to facilitate reproducible evaluation and comparison of continual reinforcement learning agents across standardized curricula and diverse environments.

Contribution

This paper introduces TELLA, a novel tool that provides reproducible curricula and detailed evaluation metrics for lifelong reinforcement learning research.

Findings

TELLA enables standardized testing across multiple environments.

It improves reproducibility in continual reinforcement learning experiments.

Researchers can easily share and compare curricula using TELLA.

Abstract

Training reinforcement learning agents that continually learn across multiple environments is a challenging problem. This is made more difficult by a lack of reproducible experiments and standard metrics for comparing different continual learning approaches. To address this, we present TELLA, a tool for the Test and Evaluation of Lifelong Learning Agents. TELLA provides specified, reproducible curricula to lifelong learning agents while logging detailed data for evaluation and standardized analysis. Researchers can define and share their own curricula over various learning environments or run against a curriculum created under the DARPA Lifelong Learning Machines (L2M) Program.